There are three basic components on Printed Circuit Board (PCB): the board, the copper, and the solder. Automatic optical inspection aims to segment the solder area and the copper area quickly where the solder is not totally coated on the copper. Therefore, a complete imaging mechanism is very important in inspecting process, which includes image extraction, color interpolation, image enhancement, and image stitching. After these four steps, we will have a complete image for a printed circuit board and we can do further inspection by human or program. In this thesis, we propose a new color interpolation to remove false color and improve the quality of PCB images. Then we will enhance PCB images and stitch then into a full image for further inspection.